Neurofuzzy control of weld penetration in gas tungsten arc welding
暂无分享,去创建一个
AbstractIn the present paper, a method using the surface geometrical parameters of the weld pool to control the weld penetration is developed. Because detection of the weld penetration is problematic and the back side maximum weld width can reflect weld penetration to some extent, a model describing the relationship between the weld pool surface geometrical parameters and the back side maximum weld width is constructed. Considering that the tungsten inert gas welding process exhibits long time lag and non-linear time dependence, a one layer neurofuzzy controller is designed and a learning algorithm is also developed. The controller can learn fuzzy rules and adjust the fuzzy rules automatically with variations of the environment. Based on the model and the controller, a control simulation and a control test for back side maximum weld width are conducted. The results show that the back side maximum weld width is well controlled.
[1] Y M Zhang,et al. Machine Vision Recognition of Weld Pool in Gas Tungsten Arc Welding , 1995 .
[2] Chin-Teng Lin,et al. A neural fuzzy control system with structure and parameter learning , 1995 .